SS-L15: Neural Spatial Audio Processing
Oral
Fri, 8 May, 14:00 - 16:00
Location: Room 111
Session Type: Oral
Session Co-Chairs: Yoshiki Masuyama, Mitsubishi Electric Research Laboratories (MERL) and Shoichi Koyama, National Institute of Informatics and Jonathan Le Roux, Mitsubishi Electric Research Laboratories (MERL) and Mirco Pezzoli, Politecnicno di Milano
Track: Special Sessions
Click the to view the manuscript on IEEE Xplore Open Preview
Fri, 8 May, 14:00 - 14:20
 

SS-L15.1: PHYSICS-INFORMED LEARNING OF NEURAL SCATTERING FIELDS TOWARDS MEASUREMENT-FREE MESH-TO-HRTF ESTIMATION
Tancrede Martinez, Diego Di Carlo, Aditya Arie Nugraha, RIKEN, Japan; Mathieu Fontaine, Télécom Paris, Institut Polytechnique de Paris, France; Kazuyoshi Yoshii, RIKEN, Japan
Fri, 8 May, 14:20 - 14:40
 

SS-L15.2: VELOCITY POTENTIAL NEURAL FIELD FOR EFFICIENT AMBISONICS IMPULSE RESPONSE MODELING
Yoshiki Masuyama, François Germain, Gordon Wichern, Chiori Hori, Jonathan Le Roux, Mitsubishi Electric Research Laboratories (MERL), United States of America
Fri, 8 May, 14:40 - 15:00
 

SS-L15.3: BEYOND OMNIDIRECTIONAL: NEURAL AMBISONICS ENCODING FOR ARBITRARY MICROPHONE DIRECTIVITY PATTERNS USING CROSS-ATTENTION
Mikko Heikkinen, Nokia, Finland; Archontis Politis, Tampere University, Finland; Konstantinos Drossos, Nokia, Finland; Tuomas Virtanen, Tampere University, Finland
Fri, 8 May, 15:00 - 15:20
 

SS-L15.4: NEURAL ACOUSTIC MULTIPOLE SPLATTING FOR ROOM IMPULSE RESPONSE SYNTHESIS
Geonwoo Baek, Jung-Woo Choi, KAIST, Korea, Republic of
Fri, 8 May, 15:20 - 15:40
 

SS-L15.5: ON THE ROLE OF TRAINABLE PARAMETERS IN DIFFERENTIABLE FEEDBACK DELAY NETWORKS
Riccardo Giampiccolo, Alessandro Ilic Mezza, Politecnico di Milano, Italy; Shoichi Koyama, National Institute of Informatics, Japan; Mirco Pezzoli, Alberto Bernardini, Fabio Antonacci, Augusto Sarti, Politecnico di Milano, Italy
Fri, 8 May, 15:40 - 16:00
 

SS-L15.6: GENCHO: ROOM IMPULSE RESPONSE GENERATION FROM REVERBERANT SPEECH AND TEXT VIA DIFFUSION TRANSFORMERS
Jackie Lin, University of Illinois at Urbana-Champaign, United States of America; Jiaqi Su, Adobe, United States of America; Nishit Anand, University of Maryland, United States of America; Zeyu Jin, Adobe, United States of America; Minje Kim, University of Illinois at Urbana-Champaign, United States of America; Paris Smaragdis, Massachusetts Institute of Technology, United States of America